Suchergebnisse
Suchergebnisse:
11. Dez. 2020 · In our ST-TR model, a Spatial Self-Attention module (SSA) is used to understand intra-frame interactions between different body parts, and a Temporal Self-Attention module (TSA) to model inter-frame correlations. The two are combined in a two-stream network which outperforms state-of-the-art models using the same input data on both ...
- Chiara Plizzari, Marco Cannici, Matteo Matteucci
- arXiv:2012.06399 [cs.CV]
- 2020
- Overview
- Contact 📌
Introduction
This repository contains the implementation of the model presented in the following paper:
Visualizations of Spatial Transformer logits
The heatmaps are 25 x 25 matrices, where each row and each column represents a body joint. An element in position (i, j) represents the correlation between joint i and joint j, resulting from self-attention.
Prerequisites
•Python3
If you have any question, do not hesitate to contact me at chiara.plizzari@mail.polimi.it. I will be glad to clarify your doubts!
Note: we include LICENSE, LICENSE_1 and LICENSE_2 in this repository since part of the code has been derived respectively from https://github.com/yysijie/st-gcn, https://github.com/leaderj1001/Attention-Augmented-Conv2d and https://github.com/kenziyuliu/Unofficial-DGNN-PyTorch/blob/master/README.md
21. Feb. 2021 · In this work, we propose a novel Spatial-Temporal Transformer network (ST-TR) which models dependencies between joints using the Transformer self-attention operator. In our ST-TR model, a Spatial Self-Attention module (SSA) is used to understand intra-frame interactions between different body parts, and a Temporal Self-Attention ...
17. Aug. 2020 · In this work, we propose a novel Spatial-Temporal Transformer network (ST-TR) which models dependencies between joints using the Transformer self-attention operator. In our ST-TR model, a Spatial Self-Attention module (SSA) is used to understand intra-frame interactions between different body parts, and a Temporal Self-Attention ...
17. Aug. 2020 · In our ST-TR model, a Spatial Self-Attention module (SSA) is used to understand intra-frame interactions between different body parts, and a Temporal Self-Attention module (TSA) to model inter-frame correlations.
Spatial-Temporal Transformer network (ST-TR) which models dependencies between joints using the Transformer self-attention operator. In our ST-TR model a Spatial Self-Attention module (SSA) is used to understand intra-frame interactions between different body parts, and a Temporal Self-Attention module (TSA) to model inter-frame correlations ...
In our ST-TR model, a Spatial Self-Attention module (SSA) is used to understand intra-frame interactions between different body parts, and a Temporal Self-Attention module (TSA) to model inter-frame correlations. The two are combined in a two-stream network which outperforms state-of-the-art models using the
